Open-weight models that run on Apple M4 Max (40-core GPU) · 128 GB

Unified memory 128 GB
Bandwidth 546 GB/s
Usable 96.0 GB

Specs: Memory · MacBook Pro (16-inch, 2024) - Tech Specs - Apple Support · Bandwidth · MacBook Pro (16-inch, 2024) - Tech Specs - Apple Support

Search Precision Context Concurrent requests Minimum speed Architecture Type Maker Sort

Fit	Model	Parameters / active	Precision	Memory	Est. speed	Longest context	Runs as
Runs well	Ming-3.0-audio-flash Ant Group	128.2B / 6.5B	Q4_K_M	76.5 / 96.0 GB	63–94 tok/s	128K	Unified memory
Runs well	Ling-3.0-flash Ant Group	127.5B / 5.1B	Q5_0	86.1 / 96.0 GB	70–105 tok/s	223K	Unified memory
Runs well	Qwen3.5-122B-A10B Alibaba Qwen	125.1B / 10B	Q5_0	84.3 / 96.0 GB	39–58 tok/s	256K	Unified memory
Runs well	Ling-3.0-flash-VL Ant Group	124.8B / 5.5B	Q5_0	84.3 / 96.0 GB	65–98 tok/s	128K	Unified memory
Runs well	gpt-oss-120b OpenAI	116.8B / 5.1B	MXFP4 (native)maker’s file	64.1 / 96.0 GB	87–130 tok/s	128K	Unified memory
Runs well	GLM-4.5-Air Zhipu AI	110.5B	Q5_K_M	78.3 / 96.0 GB	20–30 tok/s	107K	Unified memory
Runs well	GLM-4.5V Zhipu AI	107.7B / 12B	Q5_K_M	76.4 / 96.0 GB	27–41 tok/s	63K	Unified memory
Runs well	GLM-4.6V Zhipu AI	107.7B	Q5_K_M	76.4 / 96.0 GB	23–35 tok/s	117K	Unified memory
Runs well	Ling-2.6-flash Ant Group	107.5B / 7.4B	Q5_K_M	75.0 / 96.0 GB	49–74 tok/s	128K	Unified memory
Runs well	Qwen3-Next-80B-A3B-Instruct Alibaba Qwen	81.3B / 3B	Q8_0maker’s file	83.1 / 96.0 GB	82–123 tok/s	256K	Unified memory
Runs well	Qwen3-Next-80B-A3B-Thinking Alibaba Qwen	81.3B / 3B	Q8_0maker’s file	83.1 / 96.0 GB	82–123 tok/s	256K	Unified memory
Runs well	Qwen3-Coder-Next Alibaba Qwen	79.7B / 3B	Q8_0maker’s file	83.1 / 96.0 GB	80–121 tok/s	256K	Unified memory
Runs well	Qwen3.5-35B-A3B Alibaba Qwen	36B / 3B	BF16 (native)maker’s file	70.5 / 96.0 GB	44–66 tok/s	256K	Unified memory
Runs well	Qwen3.6-35B-A3B Alibaba Qwen	36B / 3B	BF16 (native)maker’s file	70.5 / 96.0 GB	44–66 tok/s	256K	Unified memory
Runs well	Qwen2.5-VL-32B-Instruct Alibaba Qwen	33.5B	Q4_0	20.4 / 96.0 GB	13–20 tok/s	125K	Unified memory
Runs well	Qwen3-VL-32B-Instruct Alibaba Qwen	33.4B	Q4_0	20.3 / 96.0 GB	13–20 tok/s	128K	Unified memory
Runs well	Qwen3-VL-32B-Thinking Alibaba Qwen	33.4B	Q4_0	20.3 / 96.0 GB	13–20 tok/s	128K	Unified memory
Runs well	Qwen2.5-32B-Instruct Alibaba Qwen	32.8B	Q4_0maker’s file	20.2 / 96.0 GB	13–20 tok/s	32K	Unified memory
Runs well	Qwen2.5-Coder-32B-Instruct Alibaba Qwen	32.8B	INT4 (AWQ / GPTQ)maker’s file	20.9 / 96.0 GB	13–19 tok/s	32K	Unified memory
Runs well	QwQ-32B Alibaba Qwen	32.8B	Q4_0	20.0 / 96.0 GB	13–20 tok/s	40K	Unified memory
Runs well	DeepSeek-R1-Distill-Qwen-32B DeepSeek	32.8B	Q4_0	20.0 / 96.0 GB	13–20 tok/s	32K	Unified memory
Runs well	Qwen3-32B Alibaba Qwen	32.8B	MLX 4bitmaker’s file	19.0 / 96.0 GB	14–21 tok/s	128K	Unified memory
Runs well	Qwen3-Omni-30B-A3B-Captioner Alibaba Qwen	31.7B	BF16 (native)maker’s file	62.8 / 96.0 GB	28–41 tok/s	64K	Unified memory
Runs well	Gemma 4 31B IT Google	31.3B	Q4_K_M	20.6 / 96.0 GB	13–19 tok/s	250K	Unified memory
Runs well	GLM-4.7-Flash Zhipu AI	31.2B	BF16 (native)maker’s file	61.5 / 96.0 GB	25–38 tok/s	195K	Unified memory
Runs well	Qwen3-VL-30B-A3B-Instruct Alibaba Qwen	31.1B	BF16 (native)maker’s file	61.5 / 96.0 GB	32–48 tok/s	128K	Unified memory
Runs well	Qwen3-VL-30B-A3B-Thinking Alibaba Qwen	31.1B	BF16 (native)maker’s file	61.5 / 96.0 GB	32–48 tok/s	128K	Unified memory
Runs well	Qwen3-30B-A3B-Instruct-2507 Alibaba Qwen	30.5B / 3.3B	BF16 (native)maker’s file	60.5 / 96.0 GB	37–55 tok/s	256K	Unified memory
Runs well	Qwen3-30B-A3B-Thinking-2507 Alibaba Qwen	30.5B / 3.3B	BF16 (native)maker’s file	60.5 / 96.0 GB	37–55 tok/s	256K	Unified memory
Runs well	Qwen3-30B-A3B Alibaba Qwen	30.5B / 3.3B	BF16 (native)maker’s file	60.5 / 96.0 GB	37–55 tok/s	128K	Unified memory
Runs well	Qwen3-Coder-30B-A3B-Instruct Alibaba Qwen	30.5B / 3.3B	BF16 (native)maker’s file	60.5 / 96.0 GB	37–55 tok/s	256K	Unified memory
Runs well	Hy-Memory-30B-A3B Tencent	30.1B / 3B	BF16 (native)maker’s file	59.6 / 96.0 GB	40–60 tok/s	63K	Unified memory
Runs well	Granite Switch 4.1 30B IBM	30B	IQ4_XS	17.6 / 96.0 GB	15–23 tok/s	128K	Unified memory
Runs well	Qwen3.5-27B Alibaba Qwen	27.8B	Q5_K_M	19.8 / 96.0 GB	13–20 tok/s	256K	Unified memory
Runs well	Qwen3.6-27B Alibaba Qwen	27.8B	Q5_K_M	19.8 / 96.0 GB	13–20 tok/s	256K	Unified memory
Runs well	Qwen3.8-27B Alibaba Qwen	27.8B	Q5_K_M	19.8 / 96.0 GB	13–20 tok/s	256K	Unified memory
Runs well	Gemma 4 26B A4B IT Google	25.8B / 3.8B	BF16 (native)maker’s file	51.0 / 96.0 GB	34–50 tok/s	250K	Unified memory
Runs well	Magistral Small 1.2 Mistral AI	24B	Q6_K	20.5 / 96.0 GB	13–19 tok/s	125K	Unified memory
Runs well	Devstral Small 1.0 Mistral AI	23.6B	Q6_K	20.2 / 96.0 GB	13–20 tok/s	125K	Unified memory
Runs well	Devstral Small 1.1 Mistral AI	23.6B	Q6_K	20.2 / 96.0 GB	13–20 tok/s	125K	Unified memory
Runs well	Magistral Small 1.0 Mistral AI	23.6B	Q6_K	20.2 / 96.0 GB	13–20 tok/s	39K	Unified memory
Runs well	Magistral Small 1.1 Mistral AI	23.6B	Q6_K	20.2 / 96.0 GB	13–20 tok/s	39K	Unified memory
Runs well	ERNIE-4.5-21B-A3B-Thinking Baidu	21.8B / 3B	BF16 (native)maker’s file	43.1 / 96.0 GB	42–63 tok/s	128K	Unified memory
Runs well	GPT OSS 20B OpenAI	20.9B / 3.6B	MXFP4 (native)maker’s file	13.6 / 96.0 GB	106–159 tok/s	128K	Unified memory
Runs well	Qwen2.5-14B-Instruct-1M Alibaba Qwen	14.8B	Q8_0	16.8 / 96.0 GB	16–24 tok/s	430K	Unified memory
Runs well	Qwen2.5-14B-Instruct Alibaba Qwen	14.8B	Q8_0maker’s file	16.9 / 96.0 GB	16–24 tok/s	32K	Unified memory
Runs well	DeepSeek-R1-Distill-Qwen-14B DeepSeek	14.8B	Q8_0	16.8 / 96.0 GB	16–24 tok/s	32K	Unified memory
Runs well	Qwen3-14B Alibaba Qwen	14.8B	MLX 8bitmaker’s file	16.1 / 96.0 GB	16–25 tok/s	128K	Unified memory
Runs well	Gemma 3 12B IT Google	12.2B	Q8_0	15.5 / 96.0 GB	17–26 tok/s	128K	Unified memory
Runs well	Qwen2.5-Omni-7B Alibaba Qwen	10.7B	Q8_0	11.6 / 96.0 GB	23–34 tok/s	32K	Unified memory
Runs well	GLM-4.6V-Flash Zhipu AI	10.3B	BF16 (native)maker’s file	20.4 / 96.0 GB	13–20 tok/s	125K	Unified memory
Runs well	Qwen3.5-9B Alibaba Qwen	9.7B	BF16 (native)maker’s file	19.1 / 96.0 GB	14–21 tok/s	256K	Unified memory
Runs well	Qianfan-VL-8B Baidu	8.8B	BF16 (native)maker’s file	18.2 / 96.0 GB	15–22 tok/s	32K	Unified memory
Runs well	Granite Switch 4.1 8B IBM	8.8B	BF16 (native)maker’s file	18.5 / 96.0 GB	14–22 tok/s	128K	Unified memory
Runs well	Qwen3-VL-8B-Instruct Alibaba Qwen	8.8B	BF16 (native)maker’s file	18.3 / 96.0 GB	15–22 tok/s	128K	Unified memory
Runs well	Qwen3-VL-8B-Thinking Alibaba Qwen	8.8B	BF16 (native)maker’s file	18.3 / 96.0 GB	15–22 tok/s	128K	Unified memory
Runs well	pplx-embed-v2-context-9b Perplexity	8.4B	Q8_0	9.1 / 96.0 GB	30–45 tok/s	256K	Unified memory
Runs well	Qwen2.5-VL-7B-Instruct Alibaba Qwen	8.3B	BF16 (native)maker’s file	16.7 / 96.0 GB	16–24 tok/s	125K	Unified memory
Runs well	Qwen3-8B Alibaba Qwen	8.2B	BF16 (native)maker’s file	17.1 / 96.0 GB	16–23 tok/s	128K	Unified memory
Runs well	DeepSeek-R1-Distill-Llama-8B DeepSeek	8B	BF16 (native)maker’s file	16.7 / 96.0 GB	16–24 tok/s	125K	Unified memory
Runs well	Gemma 4 E4B Google	8B	BF16 (native)maker’s file	15.8 / 96.0 GB	17–25 tok/s	125K	Unified memory
Runs well	Ling-3.0-tiny Ant Group	7.9B / 1.3B	BF16 (native)maker’s file	15.6 / 96.0 GB	97–145 tok/s	128K	Unified memory
Runs well	Qwen2.5-7B-Instruct-1M Alibaba Qwen	7.6B	BF16 (native)maker’s file	15.3 / 96.0 GB	17–26 tok/s	977K	Unified memory
Runs well	Qwen2.5-7B-Instruct Alibaba Qwen	7.6B	BF16 (native)maker’s file	15.3 / 96.0 GB	17–26 tok/s	32K	Unified memory
Runs well	DeepSeek-R1-Distill-Qwen-7B DeepSeek	7.6B	BF16 (native)maker’s file	15.3 / 96.0 GB	17–26 tok/s	32K	Unified memory
Runs well	Mistral-7B-Instruct-v0.1 Mistral AI	7.2B	BF16 (native)maker’s file	15.2 / 96.0 GB	18–26 tok/s	32K	Unified memory
Runs well	Gemma 4 E2B Google	5.1B	BF16 (native)maker’s file	10.1 / 96.0 GB	26–40 tok/s	125K	Unified memory
Runs well	WeVisOne-VL-4B Tencent	4.8B	BF16 (native)maker’s file	10.6 / 96.0 GB	25–38 tok/s	256K	Unified memory
Runs well	Qianfan-OCR Baidu	4.7B	BF16 (native)maker’s file	10.5 / 96.0 GB	26–38 tok/s	31K	Unified memory
Runs well	Qwen3.5-4B Alibaba Qwen	4.7B	BF16 (native)maker’s file	9.4 / 96.0 GB	28–43 tok/s	256K	Unified memory
Runs well	Qwen3-VL-4B-Instruct Alibaba Qwen	4.4B	BF16 (native)maker’s file	9.9 / 96.0 GB	27–41 tok/s	250K	Unified memory
Runs well	Qwen3-4B-Instruct-2507 Alibaba Qwen	4B	BF16 (native)maker’s file	9.1 / 96.0 GB	30–44 tok/s	256K	Unified memory
Runs well	Qwen3-4B Alibaba Qwen	4B	BF16 (native)maker’s file	9.1 / 96.0 GB	30–44 tok/s	128K	Unified memory
Runs well	DeepSeek-OCR DeepSeek	3.3B	BF16 (native)maker’s file	7.2 / 96.0 GB	98–147 tok/s	8K	Unified memory
Runs well	Granite-4.0-H-Micro IBM	3.2B	BF16 (native)maker’s file	6.5 / 96.0 GB	42–63 tok/s	128K	Unified memory
Runs well	Qwen3-1.7B Alibaba Qwen	2B	BF16 (native)maker’s file	5.2 / 96.0 GB	55–82 tok/s	40K	Unified memory
Runs well	DeepSeek-R1-Distill-Qwen-1.5B DeepSeek	1.8B	BF16 (native)maker’s file	4.0 / 96.0 GB	72–108 tok/s	125K	Unified memory
Runs well	GLM-OCR Zhipu AI	1.3B	BF16 (native)maker’s file	3.5 / 96.0 GB	86–128 tok/s	128K	Unified memory
Runs well	Qwen3-0.6B Alibaba Qwen	0.8B	BF16 (native)maker’s file	2.8 / 96.0 GB	112–168 tok/s	40K	Unified memory
Runs well	EmbeddingGemma 2 Google	0.7B	BF16 (native)maker’s file	2.0 / 96.0 GB	173–260 tok/s	256K	Unified memory
Runs well	Qwen3-Embedding-0.6B Alibaba Qwen	0.6B	BF16 (native)maker’s file	2.5 / 96.0 GB	128–192 tok/s	32K	Unified memory
Runs well	bge-reranker-v2-m3 BAAI	0.6B	FP32 (native)maker’s file	3.4 / 96.0 GB	89–133 tok/s	8K	Unified memory
Runs well	bge-m3-unsupervised BAAI	0.6B	FP32 (native)maker’s file	3.4 / 96.0 GB	89–133 tok/s	8K	Unified memory
Runs well	bge-large-en-v1.5 BAAI	0.3B	FP32 (native)maker’s file	1.8 / 96.0 GB	196–294 tok/s	512	Unified memory
Runs well	bge-reranker-base BAAI	0.3B	FP32 (native)maker’s file	1.6 / 96.0 GB	241–362 tok/s	514	Unified memory
Runs well	bge-base-en-v1.5 BAAI	0.1B	FP32 (native)maker’s file	0.9 / 96.0 GB	598–896 tok/s	512	Unified memory
Runs well	bge-small-en-v1.5 BAAI	0B	FP32 (native)maker’s file	0.6 / 96.0 GB	1910–2866 tok/s	512	Unified memory
Runs, slowly	Qwen2.5-VL-72B-Instruct Alibaba Qwen	73.4B	Q8_0	78.8 / 96.0 GB	3–5 tok/s	63K	Unified memory
Runs, slowly	Qwen2-VL-72B-Instruct Alibaba Qwen	73.4B	Q8_0	78.8 / 96.0 GB	3–5 tok/s	32K	Unified memory
Runs, slowly	Qwen2.5-72B-Instruct Alibaba Qwen	72.7B	Q8_0maker’s file	78.3 / 96.0 GB	3–5 tok/s	32K	Unified memory
Runs, slowly	Qianfan-VL-70B Baidu	71.8B	Q8_0	77.1 / 96.0 GB	3–5 tok/s	32K	Unified memory
Runs, slowly	DeepSeek-R1-Distill-Llama-70B DeepSeek	70.6B	Q8_0	75.8 / 96.0 GB	4–5 tok/s	72K	Unified memory

Estimates from the makers’ Hugging Face repositories (as of 2026-11-06); filtered views aren’t indexed. How it’s estimated